© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 40471
    Prev
    Next
    INDEX
    Explanations

    socialize and social activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.61
    一个小
    0.56
    ोटा
    0.56
    ется
    0.55
    า
    0.55
     Logical
    0.54
    察
    0.54
    Ø
    0.53
    ح
    0.52
    osaurs
    0.51
    POSITIVE LOGITS
     histórias
    0.72
     minhas
    0.71
     grados
    0.68
    부가
    0.68
    냔
    0.67
     Enseñ
    0.66
    ່າຍ
    0.66
    τε
    0.65
     identidade
    0.65
    e
    0.64
    Activations Density 0.005%

    No Known Activations